With the advancement of artificial intelligence technology, certain machine learning models have gradually been applied in the field of geotechnical engineering. These models aim to accurately predict the surface settlement caused by shield tunneling and facilitate the timely implementation of appropriate measures. Leveraging data from the construction of the Shanghai Beiheng Tunnel’s super large diameter shield tunneling, three types of machine learning models were employed: random forest (RF), support vector machines (SVM), and extreme gradient boosting (XGBoost). Geological, geometric, and advancement parameters were utilized as inputs to forecast the final surface settlement resulting from the excavation of a super large diameter shield tunnel. A genetic algorithm (GA) was used to obtain the optimal hyperparameters for each machine learning model. Using the initial 70 data points within a specific section as the foundational training set, dynamic predictions were made for 27 subsequent data points. This allowed for the assessment of the models’ accuracy in predicting the final surface settlement. The results indicated that the SVM’s predictive performance was relatively poor (with a mean squared error (MSE) of 5.06 and a coefficient of determination (R2) of 0.13). In contrast, the two decision-tree-based ensemble algorithms (RF and XGBoost) exhibited better predictive results for surface settlement. Specifically, RF demonstrated an MSE of 1.35 and an R2 of 0.70, whereas XGBoost had an MSE of 2.2 and an R2 of 0.57. These ensemble algorithms can accurately predict the final surface settlement and thereby provide a novel approach for controlling construction and predicting surface settlement in the context of super large diameter slurry shield tunneling in soft soil regions.
ZHENG Chenlu
,
ZHANG Mengxi
,
WU Huiming
,
LI Gang
. Prediction of surface subsidence in super large diameter mud-water balance shield construction based on a machine learning algorithm[J]. Journal of Shanghai University, 2026
, 32(3)
: 544
-553
.
DOI: 10.12066/j.issn.1007-2861.2533
[1] 孙恒, 冯亚丽. 全球超大直径隧道掘进机数据统计[J]. 隧道建设(中英文), 2020, 40(6): 921-928.
[2] Peck R B. Deep excavations and tunneling in soft ground [C]// Proc 7th International Conference on Soil Mechanics and Foundations Engineering. 1969: 225-290.
[3] Cattoni E, Miriano C, Boco L, et al. Time dependent ground movements induced by shield tunneling in soft clay: a parametric study [J]. Acta Geotechnica, 2016, 11(6): 1385-1399.
[4] 魏纲. 盾构法隧道施工引起的土体变形预测[J]. 岩石力学与工程学报, 2009, 28(2): 418-424.
[5] 卢健, 姚爱军, 郑轩, 等. 地铁双线隧道开挖地表沉降规律及计算方法研究[J]. 岩石力学与工程学报, 2019, 38(S2): 3735-3747.
[6] 李洛宾, 龚晓南, 甘晓露, 等. 基于循环神经网络的盾构隧道引发地面最大沉降预测[J]. 土木工程学报, 2020, 53(S1): 13-19.
[7] Ye X W, Jin T, Chen Y M. Machine learning-based forecasting of soil settlement induced by shield tunneling construction [J]. Tunnelling and Underground Space Technology, 2022, 124(2): 104452.
[8] 荣雪宁, 刘旭东, 文祝, 等. 基于人工神经网络的砂卵石地层盾构地表沉降预测[J]. 地下空间与工程学报, 2022, 18(S2): 958-966.
[9] 陈仁朋, 戴田, 张品, 等. 基于机器学习算法的盾构掘进地表沉降预测方法[J]. 湖南大学学报(自然科学版), 2021, 48(7): 111-118.
[10] 吴贤国, 冯宗宝, 刘俊, 等. 基于RF-NSGA-Ⅱ 的盾构施工地表沉降安全控制多目标优化[J]. 中国安全科学学报, 2022, 32(8): 45-51.
[11] 方小明, 张孟喜, 张梓升, 等. 超大直径盾构掘进引起地表纵向变形规律分析[J]. 人民长江, 2021, 52(7): 160-167.
[12] 周志华. 机器学习[M]. 北京: 清华大学出版社, 2016.
[13] Chen T, Guestrin C. XGBoost: a scalable tree boosting system [C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016: 785-794.
[14] Ding L, Wang F, Luo H, et al. Feedforward analysis for shield-ground system [J]. Journal of Computing in Civil Engineering, 2013, 27(3): 231-242.
[15] Goh A T C, Hefney A M. Reliability assessment of EPB tunnel-related settlement [J]. Geomech Eng, 2010, 2(1): 57-69.
[16] Kohestani V R, Bazarganlari M R, Asgari M J. Prediction of maximum surface settlement caused by earth pressure balance shield tunneling using random forest [J]. Journal of AI and Data Mining, 2017, 5(1): 127-135.
[17] 宋蕴璞, 徐宝福. 大型泥水平衡盾构气泡舱初始参数的设计[J]. 同济大学学报(自然科学版), 2010, 38(8): 1221-1225.
